v3.0.0-beta.43

3.0.0-beta.43 (2024-08-09)

Bug Fixes

• more cases of unknown characters in generation streaming (#295) (ecaef63)

---

Shipped with llama.cpp release b3560

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v3.0.0-beta.42

3.0.0-beta.42 (2024-08-07)

Bug Fixes

• unkown characters in generation streaming (#293) (097b3ec)

---

Shipped with llama.cpp release b3541

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v2.8.15

2.8.15 (2024-08-06)

Bug Fixes

• adapt to llama.cpp breaking changes (#291) (c4b5d80)

v3.0.0-beta.41

3.0.0-beta.41 (2024-08-02)

Bug Fixes

• CUDA context creation (#285) (a2b2bc3)
• detokenizer unpredictable text length (#285) (a2b2bc3)

---

Shipped with llama.cpp release b3504

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v3.0.0-beta.40

3.0.0-beta.40 (2024-07-30)

Bug Fixes

• update model recommendations (#276) (826334b)

Features

• model downloader: use HF_TOKEN when needed (#276) (826334b)

---

Shipped with llama.cpp release b3488

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v3.0.0-beta.39

3.0.0-beta.39 (2024-07-28)

Bug Fixes

• Gemma chat wrapper bug (#273) (e3e0994)
• GGUF metadata nested key conflicts (#273) (e3e0994)
• adapt to llama.cpp breaking changes (#273) (e3e0994)
• preserve function calling chunks (#273) (e3e0994)
• format JSON objects like models expect (#273) (e3e0994)

Features

• Llama 3.1 support (#273) (e3e0994)
• Phi-3 support (#273) (e3e0994)
• model metadata overrides (#273) (e3e0994)
• use LoRA on a context instead of on a model (#273) (e3e0994)
• onTextChunk option (#273) (e3e0994)

---

Shipped with llama.cpp release b3479

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v2.8.14

2.8.14 (2024-07-26)

Bug Fixes

• prebuilt binaries (#272) (e539e5b)

v2.8.13

2.8.13 (2024-07-26)

Bug Fixes

• adapt to llama.cpp breaking changes (#271) (7f15823)

v3.0.0-beta.38

3.0.0-beta.38 (2024-07-09)

Bug Fixes

• adapt to llama.cpp breaking changes (#266) (c35ff5a)
• Llama 3 Instruct function calling (#266) (c35ff5a)

Features

• flash attention in model selection (#266) (c35ff5a)

---

Shipped with llama.cpp release b3347

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)

v3.0.0-beta.37

3.0.0-beta.37 (2024-07-05)

Features

• flash attention (#264) (c2e322c)
• manually exclude specific GPU types from gpu: "auto" (#264) (c2e322c)

---

Shipped with llama.cpp release b3322

To use the latest llama.cpp release available, run npx --no node-llama-cpp download --release latest. (learn more)